Deployments And Environments

Operator validates v2 of a model on /development/predict and clicks 'Promote to Production' in the workspace UI.

Promotion atomically points the production URL at the dev-tested image. In-flight production requests against the old image complete on their replicas; new requests are routed to the new image as replicas come up. Treat promotion as a release event and tag it in the operator's deploy log.

v2 fails in production with elevated 5xx. Operator clicks 'Rollback' to v1 in the deployments UI.

Rollback re-routes production URL traffic to the prior image. v2 replicas drain their in-flight requests and terminate. Confirm rollback by observing replica counts and error rate restore. The rollback action does NOT delete v2 — keep it for forensics.

Two engineers push to /development/predict at the same time. Each clobbers the other's dev image.

Development is a single shared environment per model — concurrent pushes race. Either coordinate via the operator's own task queue, create per-engineer model names for parallel iteration, or use a feature-branch model. Do not assume dev preserves multiple in-flight versions.